The Application Of Computer Vision And Labview In Fabric Deffects Detection

In the whole process of fabric manufacturing, fabric defects detection is an important procedure. So far, the traditional fabric defects detection is completed manually, which is a dull, tedious and tiring work. The result is easily influenced by the worker's ability, his mentality condition and his physiological state, meanwhile, it is inefficient. With the development of computer and digital image processing technique, the computer vision is more and more frequently applied in industrial production. The computer vision-based automatic fabric defects detection has become one of the research focuses.In this thesis, the achievements of researches in fabric defects detection have been analyzed at first. By doing this, a conclusion that although these researches can get high accuracy in fabric detection, they usually have unsatisfactory detection speed and environment adaptation has been reached. So, according to the practical application, the aim of this thesis is to set up a detection system which has agreeable accuracy and obvious advantage in detection speed than previous researches.Next, the general construction of the detection system and the basic principles and parameters of the hardware have been introduced. In this system, the line-scan CCD camera has been used, because the line-scan camera has advantages in light control and photographing objects moving in high speed compared to matrix CCD camera.Then, the software LabVIEW used in this system has been introduced. LabVIEW is a product of National Instrument. It's a graphical programming language that has been widely adopted throughout the world. It has been used in instrument control, data collection, data analysis, date display and so on. With its powerful graphical programming language, creating a LabVIEW program or virtual instrument (VI) is simple. LabVIEW's intuitive user interface makes writing and using programs exciting and fun.In the last part of this thesis, the process of dealing with the fabric image using curve fitting method has been studied. The curve fitting method was used to stand out the defects in fabric. The method has been found effective and with higher detection speed than previous researches by testing its effects to different defects in different working environment. After standing out the defects, the binarization was done by using statistical threshold segmentation. The process of getting the parameters of defects including the locations in the running direction and width direction, the length, the width, the ratio of length to width has been introduced in details too.